Ross Girshick

About

Ross Girshick is a leading figure in computer vision, best known for his foundational contributions to object detection and deep learning. His research focuses on developing algorithms that enable machines to perceive and understand visual scenes, particularly through the integration of RGB and depth (RGB-D) data. Girshick’s most cited work, "Learning Rich Features from RGB-D Images for Object Detection and Segmentation" (2014, with over 1,530 citations), introduced a novel geocentric embedding for depth images that encodes height above ground and angle with gravity, alongside horizontal disparity. This approach significantly improved the semantic richness of features for object detection and segmentation tasks, demonstrating how depth information can enhance visual recognition. By bridging 2D and 3D understanding, Girshick’s methods have influenced a wide range of applications, from robotics to autonomous systems. His work has been widely adopted, with thousands of citations underscoring its impact on the field. Girshick continues to shape computer vision research, advancing the frontier of how machines learn from multimodal visual data.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning Rich Features from RGB-D Images for Object Detection and Segmentation

   1,531 citations · 2014
2. 2
   Editorial- Deep Learning for Computer Vision

   13 citations · 2017
3. 3
   Learning Rich Features from RGB-D Images for Object Detection and\n Segmentation

   10 citations · 2014

Key Collaborators

Contact & Links